{ "task": "countdown", "models": [ { "model": "Base", "pass@1": 0.15234375, "pass@8": 0.52734375, "valid_expression_rate": 0.14111328125, "valid_expression_diversity": 0.79296875, "mean_response_tokens": 1775.06640625 }, { "model": "RLVR", "pass@1": 0.57421875, "pass@8": 0.88671875, "valid_expression_rate": 0.56787109375, "valid_expression_diversity": 2.01171875, "mean_response_tokens": 1737.57421875 } ] }